aaro765 commited on
Commit
605ce9e
·
1 Parent(s): f587b21

Update README.md (#1)

Browse files

- Update README.md (a45aa06bf806cb820de86a3aee81b7ac96d009a8)

Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -10,4 +10,9 @@ license: apache-2.0
10
  | BanBTP V2 | Gemma 4 | 31B | 1M | Obsolete | Heavy — needs 200GB+ RAM. Inconsistent reasoning. |
11
  | BanBTP V3 | Gemma 4 | 5B | 1M | Current flagship | Stable, remembers facts, thinks through problems |
12
  | BanBTP V4 (coder) | Gemma 4 | 5B | 1M | Public variant | Fine-tuned for coding + reasoning only |
13
- | **BanBTP INFINITE** | **Custom architecture (distilled from V3 + V4)** | **Unknown** | **2M** | **Closed source / Flagship** | Combines chat + coding. Beats V2 easily. |
 
 
 
 
 
 
10
  | BanBTP V2 | Gemma 4 | 31B | 1M | Obsolete | Heavy — needs 200GB+ RAM. Inconsistent reasoning. |
11
  | BanBTP V3 | Gemma 4 | 5B | 1M | Current flagship | Stable, remembers facts, thinks through problems |
12
  | BanBTP V4 (coder) | Gemma 4 | 5B | 1M | Public variant | Fine-tuned for coding + reasoning only |
13
+ | **BanBTP INFINITE** | **Custom architecture (distilled from V3 + V4)** | **Unknown** | **2M** | **Closed source / Flagship** | Combines chat + coding. Beats V2 easily. |
14
+
15
+ largest doesn't always mean better.
16
+
17
+
18
+ Thanks to: the Gemma team for creating the Gemma4 models! <3